hook-master
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including video scripts, viewer comments, and direct messages, which introduces an attack surface for indirect prompt injection.
- Ingestion points: The skill gathers information from the user in 'Step 0: Get the facts' and 'Stage 5: Niche', specifically incorporating viewer comments and direct messages into the generated hooks.
- Boundary markers: The instructions lack requirements for using delimiters or explicit markers to isolate untrusted user input from the agent's core instructions.
- Capability inventory: The skill is designed to interact with the environment by loading additional skills through named tools and reading files from sibling directories ('..//SKILL.md').
- Sanitization: No sanitization, filtering, or validation of user-provided examples or audience comments is specified in the instruction set.
Audit Metadata